Averaging covariance matrices for EEG signal classification based on the CSP: An empirical study

This paper presents an empirical comparison of covariance matrix averaging methods for EEG signal classification. Indeed, averaging EEG signal covariance matrices is a key step in designing brain-computer interfaces (BCI) based on the popular common spatial pattern (CSP) algorithm. BCI paradigms are...

Full description

Saved in:
Bibliographic Details
Published in:2015 23rd European Signal Processing Conference (EUSIPCO) pp. 2721 - 2725
Main Authors: Yger, Florian, Lotte, Fabien, Sugiyama, Masashi
Format: Conference Proceeding
Language:English
Published: EURASIP 01.08.2015
Subjects:
brain-computer interface (BCI)
common spatial pattern
Covariance matrices
EEG signal classification
Electroencephalography
Europe
Feature extraction
Geometry
Riemannian geometry
robust averaging
Signal processing
SPD matrices
Symmetric matrices
ISSN:2076-1465
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract This paper presents an empirical comparison of covariance matrix averaging methods for EEG signal classification. Indeed, averaging EEG signal covariance matrices is a key step in designing brain-computer interfaces (BCI) based on the popular common spatial pattern (CSP) algorithm. BCI paradigms are typically structured into trials and we argue that this structure should be taken into account. Moreover, the non-Euclidean structure of covariance matrices should be taken into consideration as well. We review several approaches from the literature for averaging covariance matrices in CSP and compare them empirically on three publicly available datasets. Our results show that using Riemannian geometry for averaging covariance matrices improves performances for small dimensional problems, but also the limits of this approach when the dimensionality increases.
AbstractList This paper presents an empirical comparison of covariance matrix averaging methods for EEG signal classification. Indeed, averaging EEG signal covariance matrices is a key step in designing brain-computer interfaces (BCI) based on the popular common spatial pattern (CSP) algorithm. BCI paradigms are typically structured into trials and we argue that this structure should be taken into account. Moreover, the non-Euclidean structure of covariance matrices should be taken into consideration as well. We review several approaches from the literature for averaging covariance matrices in CSP and compare them empirically on three publicly available datasets. Our results show that using Riemannian geometry for averaging covariance matrices improves performances for small dimensional problems, but also the limits of this approach when the dimensionality increases.
Author Yger, Florian
Sugiyama, Masashi
Lotte, Fabien
Author_xml – sequence: 1
  givenname: Florian
  surname: Yger
  fullname: Yger, Florian
  organization: Dept. of Complexity Sci. & Eng., Univ. of Tokyo, Tokyo, Japan
– sequence: 2
  givenname: Fabien
  surname: Lotte
  fullname: Lotte, Fabien
  organization: Inria Bordeaux Sud-Ouest LaBRI, Talence, France
– sequence: 3
  givenname: Masashi
  surname: Sugiyama
  fullname: Sugiyama, Masashi
  organization: Dept. of Complexity Sci. & Eng., Univ. of Tokyo, Tokyo, Japan
BookMark eNotkMtuwjAURN2qlUopX9Au_AOh10786g5FgSIhgURZU8e-oZbAQXGKxN83UlnNWcyZxTyTh9hGJOSNwZQxMO_VbrvclOspByamKpdcK3NHJkZpMIZryWWe35MRByUzVkjxRCYphRq4Bq0YyBH5nl2ws4cQD9S1F9sFGx3Sk-274DDRpu1oVS1oCodoj9Qd7eA3wdk-tJHWNqGnA_Q_SMvt5oPOIsXTOQzy0E79r7--kMfGHhNObjkmu3n1VX5mq_ViWc5WWeAF67MGfdFw5b3Iaw0gsHa1BAWgDRiEnDXcGJTeM0SrhZfc1cIKLTgYVwibj8nr_25AxP25CyfbXfe3T_I_ObZYPg
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/EUSIPCO.2015.7362879
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9780992862633
0992862639
EISSN 2076-1465
EndPage 2725
ExternalDocumentID 7362879
Genre orig-research
GroupedDBID 6IE
6IL
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i241t-fed4f27dd53b8005ebcb607008909e031f299e6dd1eea85d62cb5a585209c45a3
IEDL.DBID RIE
ISICitedReferencesCount 35
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000377943800546&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:54:47 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i241t-fed4f27dd53b8005ebcb607008909e031f299e6dd1eea85d62cb5a585209c45a3
PageCount 5
ParticipantIDs ieee_primary_7362879
PublicationCentury 2000
PublicationDate 2015-08
PublicationDateYYYYMMDD 2015-08-01
PublicationDate_xml – month: 08
  year: 2015
  text: 2015-08
PublicationDecade 2010
PublicationTitle 2015 23rd European Signal Processing Conference (EUSIPCO)
PublicationTitleAbbrev EUSIPCO
PublicationYear 2015
Publisher EURASIP
Publisher_xml – name: EURASIP
SSID ssib028087106
ssib025355106
Score 1.8006779
Snippet This paper presents an empirical comparison of covariance matrix averaging methods for EEG signal classification. Indeed, averaging EEG signal covariance...
SourceID ieee
SourceType Publisher
StartPage 2721
SubjectTerms brain-computer interface (BCI)
common spatial pattern
Covariance matrices
EEG signal classification
Electroencephalography
Europe
Feature extraction
Geometry
Riemannian geometry
robust averaging
Signal processing
SPD matrices
Symmetric matrices
Title Averaging covariance matrices for EEG signal classification based on the CSP: An empirical study
URI https://ieeexplore.ieee.org/document/7362879
WOSCitedRecordID wos000377943800546&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELbaioEJUIt4ywMjaV03jm22qkqBpUQqlboVx75IlehDff1-zm4oILGwWRmiyHfn77v47jtC7guveeZARyZWLIodx5BSkEeiMMyiSylgLgybkIOBGo91ViEPh14YAAjFZ9D0y3CX7xZ263-VtSSetkrqKqlKKfe9Wl--wwUC548bQ64YpgIsKbvl2ky30tHwJeu9-nIu0Sxf9WumSoCU_sn_PuaUNL5782h2QJ0zUoF5nbx30SPDvCFqFztMf70t6SzI78OaIjGlafpEfbGG-aDWM2ZfIhSsQj2QOYoL5IK0N8weaXdOYbacBvUQGgRoG2TUT996z1E5OyGaIiZvogJcXHDpnOjkyAkF5DZPMLyZ0kwDRnKBOASJc20Ao4RLuM2FwdyBM21jYTrnpDZfzOGCUA9umjtpBFJFAVJ1cuOQJSARUpZLeUnqfncmy708xqTcmKu_H1-TY2-AfQ3dDaltVlu4JUd2t5muV3fBpp-skaE0
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwIxEG0QTfSkBozf9uDRhVK2bNcbIasQETcBEm7YbWcTElkIX7_faVlREy_emj1sNp2ZvjfbmTeE3KdW88xA6ClfMs83HENKQuKJVDGNLiWBGTdsIuj15GgUxgXysOuFAQBXfAYVu3R3-Wam1_ZXWTXA01YG4R7ZF77Pa9turS_v4QKh88edIZcMkwHWyPvlaiysRsN-J2692YIuUclf9muqigOVp-P_fc4JKX9359F4hzunpABZibw30SfdxCGqZxtMgK016dQJ8MOSIjWlUfRMbbmG-qDacmZbJOTsQi2UGYoLZIO01Y8faTOjMJ1PnH4IdRK0ZTJ8igattpdPT_AmiMorLwXjpzwwRtQTZIUCEp00MMCZDFkIGMspIhE0jKkBKClMg-tEKMweOAu1L1T9jBSzWQbnhFp4C7kJlECyKCCQ9UQZ5AlIhaTmQXBBSnZ3xvOtQMY435jLvx_fkcP24LU77nZ6L1fkyBpjW1F3TYqrxRpuyIHerCbLxa2z7yc_yKR7
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2015+23rd+European+Signal+Processing+Conference+%28EUSIPCO%29&rft.atitle=Averaging+covariance+matrices+for+EEG+signal+classification+based+on+the+CSP%3A+An+empirical+study&rft.au=Yger%2C+Florian&rft.au=Lotte%2C+Fabien&rft.au=Sugiyama%2C+Masashi&rft.date=2015-08-01&rft.pub=EURASIP&rft.eissn=2076-1465&rft.spage=2721&rft.epage=2725&rft_id=info:doi/10.1109%2FEUSIPCO.2015.7362879&rft.externalDocID=7362879